Instructions to use OpenNLPLab/TransNormerLLM-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenNLPLab/TransNormerLLM-1B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OpenNLPLab/TransNormerLLM-1B", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-1B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenNLPLab/TransNormerLLM-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenNLPLab/TransNormerLLM-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenNLPLab/TransNormerLLM-1B

SGLang

How to use OpenNLPLab/TransNormerLLM-1B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OpenNLPLab/TransNormerLLM-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OpenNLPLab/TransNormerLLM-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenNLPLab/TransNormerLLM-1B with Docker Model Runner:
```
docker model run hf.co/OpenNLPLab/TransNormerLLM-1B
```

TransNormerLLM-1B

Commit History

Nov 3, 2024

18:41
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
5d59871

Feb 26, 2024

03:39
Upgrade to lightning att2

OpenNLPLab

Verified signature
2a0691e

Jan 26, 2024

09:49
Upload modeling_transnormer.py

OpenNLPLab

Verified signature
def6113

Nov 17, 2023

04:12
Fix issues regarding to transformer version

OpenNLPLab

460b22e

Nov 13, 2023

10:39
Update README.md

OpenNLPLab

cf95141

Oct 17, 2023

07:31
Update README.md

OpenNLPLab

9cc4c3a

Oct 16, 2023

13:23
Upload Community License for TransNormerLLM Model.pdf

OpenNLPLab

01e8849
09:51
Update README.md

OpenNLPLab

170779b
09:50
Upload TransNormerLLM模型社区许可协议.pdf

OpenNLPLab

eb9777a
09:50
Update README.md

OpenNLPLab

cc8ed47
08:43
Update README.md

OpenNLPLab

4b20cb5
06:36
Update README.md

OpenNLPLab

0555270

Oct 15, 2023

04:03
Upload pytorch_model.bin

OpenNLPLab

f9edef6
03:53
Update README.md

OpenNLPLab

e0236f3
03:31
Publish 1B Model

OpenNLPLab

92d0fa0

Oct 14, 2023

16:53
initial commit

OpenNLPLab

ec12bd9

Commit History

Nov 3, 2024

Adding `safetensors` variant of this model⁠

Feb 26, 2024

Upgrade to lightning att2

Jan 26, 2024

Upload modeling_transnormer.py

Nov 17, 2023

Fix issues regarding to transformer version

Nov 13, 2023

Update README.md

Oct 17, 2023

Update README.md

Oct 16, 2023

Upload Community License for TransNormerLLM Model.pdf

Update README.md

Upload TransNormerLLM模型社区许可协议.pdf

Update README.md

Update README.md

Update README.md

Oct 15, 2023

Upload pytorch_model.bin

Update README.md

Publish 1B Model

Oct 14, 2023

initial commit